Search Query Processing via Metadata Extraction and Category Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines for prior art in patent databases are inefficient and time-consuming, often failing to effectively utilize patent classes and keyword combinations, leading to irrelevant search results and wasted time during the identification of similar documents.
Innovation Solution
A computer-implemented method and system that processes search queries by extracting metadata from input documents, ranking categories based on document associations, excluding predefined categories, and forming optimized search queries by combining metadata and categories, which are then used to search databases for relevant output documents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional search engines are used to search patent databases, then users can identify prior art documents, but the process is cumbersome and time-consuming
Solution Approach 1:
The system performs preliminary actions by pre-processing patent documents to extract metadata, keywords, and categorize them into IPC/CPC classes before search requests are made. This pre-organization of data structure enables rapid retrieval during actual search operations, significantly reducing search time while maintaining productivity
Solution Approach 2:
The system introduces an intermediary processing layer that sits between the user's search request and the patent database. This intermediary automatically generates optimized search queries by combining keywords and patent classes, acting as a mediator that transforms simple user input into sophisticated search operations without requiring user involvement in the complex query formation process
2Reliability
If existing search engines focus on keywords only, then search queries are simple to form, but patent classes are not effectively utilized leading to less relevant results
Solution Approach 1:
The system merges multiple search elements (keywords from patent documents and IPC/CPC classification codes) into a unified search query structure. By combining these different types of data elements, the system creates more comprehensive and relevant search results while automatically handling the complexity of query formation, making the process simple for users despite the sophisticated underlying mechanisms
3Measurement precision
If search queries include all metadata and categories, then comprehensive coverage is achieved, but irrelevant results increase and search precision decreases
Solution Approach 1:
The system extracts and utilizes specific high-value elements from patent documents (metadata, keywords, and classification codes) while discarding irrelevant information. This selective extraction process maintains comprehensive coverage of important aspects while filtering out noise that would otherwise reduce precision and inflate result quantities with irrelevant documents
Data Source
AI summary
A computer-implemented method for forming a search query includes receiving a search request for searching at least one output document based on a first input document, extract a first metadata from the first input document, a second metadata from at least one second input document, and a third metadata from synonyms of the first and second metadata, form a first set of metadata by combining the first, second and third metadata, rank a first set of categories, wherein a category associated with a highest number of input documents is ranked highest, forming a second set of categories by excluding a predefined number of categories, forming a second set of metadata by excluding at least one definition metadata from the first set of metadata, and forming a search query by combining the second set of metadata and second set of categories.